© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 12113
    Prev
    Next
    INDEX
    Explanations

    contains fat or oil

    np_acts-logits-general · gemini-2.5-flash-lite

    food ingredients and nutritional components in descriptions of food products.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects mentions of specific food ingredients or additives (e.g. chemical or component names in ingredient lists).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    strukturen
    -0.79
     manuelle
    -0.75
     bemerk
    -0.71
     retos
    -0.70
    ejemplo
    -0.70
    털
    -0.69
    '";
    -0.68
    рам
    -0.68
     hemsida
    -0.68
    '></
    -0.68
    POSITIVE LOGITS
     cane
    1.02
     isolated
    0.96
     mal
    0.94
     wheat
    0.93
     vegetable
    0.91
     dext
    0.90
     corn
    0.86
     де
    0.85
    Isolated
    0.84
    Mal
    0.81
    Activations Density 0.021%

    No Known Activations